1 / 20

Analytical Designs (Part 2): Observational Study Designs

NTR 694 – Week 2. Analytical Designs (Part 2): Observational Study Designs. Observational Studies. Study in which the treatment or exposure of interest is not assigned, but occurs by choice or happenstance

miller
Download Presentation

Analytical Designs (Part 2): Observational Study Designs

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. NTR 694 – Week 2 Analytical Designs (Part 2):Observational Study Designs

  2. Observational Studies • Study in which the treatment or exposure of interest is not assigned, but occurs by choice or happenstance • Depend on people’s natural or voluntary exposures to factors not ordinarily randomly assigned • Always the possibility that the exposed and unexposed differ in important ways other than “exposure”

  3. PreExperimental Designs • Case study (Single Subject) design • One group pre test post test • Static group comparison design

  4. Single-subject research • Single-subject research design involves studying a single individual or system by taking baseline (to act as comparison to measurements after manipulations) then repeated measurements of one or more dependent variables and systematically applying and sometimes withdrawing or varying the independent variable. • Why use single subject design? • Not enough subjects to follow a group design • Extensive and ongoing observation are required • Individual responses to treatment are desired

  5. Single-Subject Designs • A-B (simple) design • Compares pretreatment with treatment • A-B-A (reversal) design • Baseline-treatment-baseline periods • A-B-A-B design • Baseline-treatment-baseline-treatment • Resolves ethical issue of leaving subject without treatment • B-A-B design • Treatment-no treatment-treatment • Used if treatment needed right away • A-B-C-B design • Baseline-treatment1-treatment2-treatment1

  6. One Group Pretest - Posttest • Single group is measured before treatment and after treatment • Better design then case study because researcher knows if changes occurred • Still weak design because many influences may determine change • Also has no control group 0 X 0 Pretest Treatment Posttest

  7. Static Group Comparison • Two already existing groups are used • Subjects are not randomly assigned to the groups • Control group either has different treatment or no treatment X 0 Treatment 1 Dependent Variables C 0 No treatment/Treatment 2 Dependent Variables

  8. Case Control Studies • Type of analytical study • A single point of observation. • Unit of observation and analysis: individual (not group) • Selection based on presence or absence of the disease status (using a pre-established diagnostic criteria). • Exposure is determined retrospectively. • Cases may be located from hospitals, clinics, disease registries, screenings, etc. • Controls may be from the same hospital, relatives of cases, etc. More than one control group of value. When ratio of controls to cases is at about a 4:1, statistical power of the design is maximal • Does not directly provide incidence data. • Compute Odds Ratio (OR) as measure of association.

  9. Overview of Case-Control Studies Target Population Cases Controls Disease NO Disease TODAY Exposed Not Exposed Exposed Not Exposed PAST PAST

  10. Case Control Studies – Odds Ratio • Odds Ratio (OR)=1 implies no association. • Assuming statistical significance: • OR = 2 suggests cases were twice as likely as controls to be exposed (etc.) • OR<1 suggests a protective factor. • An OR provides a good approximation of risk when: • Controls are representative of a target population • Cases are representative of all cases • The frequency of disease in the population is small

  11. Case Control Studies Advantages Limitations Provide indirect estimate of risk Timing of exposure-disease relationship difficult to determine. Representativeness of cases and controls often unknown. • Tend to use smaller sample sizes than surveys or prospective studies. • Able to study several risk factors for a single disease • Quick and easy to complete. • Cost effective. • Useful for studies of rare diseases compared to cohort studies. • Because need only few cases

  12. Cohort Studies • A cohort is defined as a population group, or subset thereof, that is followed over a period of time. • Cohort group members experience a common exposure associated with a specific setting (e.g., an occupational cohort or a school cohort) or they share a non-specific exposure associated with a general classification (e.g., a birth cohort—being born in the same year or era). • Permit the calculation of incidence rates. • Can be thought of as going from cause to effect. • Population-based cohort studies are not efficient for rare exposures • Exposure-based cohort is made up of subjects with a common exposure, for example, workers exposed to lead during battery production. Certain groups, such as occupational groups, may have higher exposures than the general population to specific hazards.

  13. Cohort Study Design POPULATION no positive history of the disease/condition of interest EXPOSED (naturally occurring; no experimental manipulation) NOT EXPOSED DEVELOP DISEASE NO DISEASE DEVELOP DISEASE NO DISEASE

  14. Types of Cohort Studies • Need to trade off between a retrospective study design (with the benefits of more immediate follow-up time) and collection of the value of collecting primary exposure data in a prospective cohort design Key: E = exposure ; D = disease (or condition) of interest

  15. Cohort Studies – Relative Risk Relative Risk (RR) = • incidence rate in the exposed • incidence rate in the non-exposure Relative Risk (RR) = [A/A+B] / [C/C+D] = (14/23)/(49/199) = 2.46 Can also compute Attributable Risk: [A/A+B] - [C/C+D]

  16. Cohort Studies Strengths Limitations Take a long time Costly Subjects lost to follow-up People may change their status with regard to risk factor/ exposure • Permit direct determination of risk. • Time sequencing of exposure and outcome. • Can detect patterns of change in both risk factors & outcomes over time. • Can study multiple outcomes. • Can study outcomes related to different levels of exposure.

  17. Causal-Comparative Research • Research using pre-existing groups to explore the cause for, or consequences of, existing differences between or among groups on the outcome (or dependent) variables; also referred to as ex post facto research. • Ex post facto (Latin for “after the fact”): Both the effect(s) and the alleged cause(s) have already occurred, and hence are studied in retrospect, so the differences have already occurred. • No manipulation of independent variable takes place. Independent Variable (presumed or possible cause) Dependent Variable (quantitative outcomes) Affects

  18. Analytic Survey • Collection of information from a sample by asking questions (often are self-administered questionnaires), in order to describe some aspects of the population of which the sample is a part. • Example: Survey on stage of change, benefits, and barriers to vegetable intake in middle school children. • Rarely is the population as a whole studied. Instead a sample is surveyed and a description of the population is inferred from what the sample reveals.

  19. Content Analysis • Content Analysis is any technique for making inferences by systematically and objectively identifying special characteristics of messages. In other words, researchers examine artifacts of social communication. • May include films, photographs, transcripts of speeches, newspaper stories, novels, journals, cookbooks, songs, advertisements, textbooks, diaries, movies, etc. • Objective analysis of messages (written or verbal) is accomplished by means of explicit rules called criteria of selection, established before the actual analysis of data. • The criteria of selection used in any given content analysis must be sufficiently exhaustive to account for each variation of message content and must be rigidly applied so that other researchers looking at the same messages would obtain the same or comparable results.

  20. Historiography • Historiography is an examination of elements from history. It involves retelling of facts from the past. • Historical research extends beyond a mere collection of incidents, facts, dates or figures. It links together pieces of information found in diaries, letters or other documents. It involves a process that examines events or combinations of events in order to uncover accounts of what happened in the past. It is a study of the relationships among issues that have influenced the past, continue to influence the present and will certainly affect the future.

More Related